arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 0709.0626math.STstat.TH
收藏

凸风险最小化下核回归的一致性和鲁棒性

Consistency and robustness of kernel-based regression in convex risk minimization

Andreas Christmann, Ingo Steinwart

摘要:

我们研究了一类广泛的现代基于核的回归(KBR)方法的统计特性。这些核方法是在过去的十年中发展起来的,其灵感来自于无限维希尔伯特空间中的凸风险最小化。一个主要的例子是支持向量回归。我们首先描述KBR方法的损失函数$L$和响应变量的尾部之间的关系。然后,我们建立了$L$的风险一致性KBR的数学理由的声明,这些方法能够“学习”。然后,我们考虑这样的核方法的鲁棒性。特别是,我们的研究结果使我们能够选择的损失函数和内核,以获得计算上易于处理和一致的KBR方法,有界影响函数。此外,界限的偏差和灵敏度曲线,这是一个有限样本版本的影响函数,开发,KBR和经典的$M$估计之间的关系进行了讨论。

英文摘要:

We investigate statistical properties for a broad class of modern kernel-based regression (KBR) methods. These kernel methods were developed during the last decade and are inspired by convex risk minimization in infinite-dimensional Hilbert spaces. One leading example is support vector regression. We first describe the relationship between the loss function $L$ of the KBR method and the tail of the response variable. We then establish the $L$-risk consistency for KBR which gives the mathematical justification for the statement that these methods are able to ``learn''. Then we consider robustness properties of such kernel methods. In particular, our results allow us to choose the loss function and the kernel to obtain computationally tractable and consistent KBR methods that have bounded influence functions. Furthermore, bounds for the bias and for the sensitivity curve, which is a finite sample version of the influence function, are developed, and the relationship between KBR and classical $M$ estimators is discussed.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑